rain cheng

A junior high school student. Like coding and learning
LLM
Thanks for your following

[rain cheng @explorer_dar]

@UnslothAI @Zai_org I was shocked that you have such fast speed!

[rain cheng @explorer_dar]

@Lonely__MH 等512

[rain cheng @explorer_dar]

@UnslothAI @Alibaba_Qwen wonderful work!😃

[rain cheng @explorer_dar]

@UnslothAI @Alibaba_Qwen faster than anyone😁, can't wait to try

[rain cheng @explorer_dar]

@UnslothAI @Zai_org waiting for GGUF

[rain cheng @explorer_dar]

How amazing arithmetic the KDA is, this arithmetic makes the token context become more smart, with well-trained alpha and beta factor, 1M-context ability will popularize soon

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[rain cheng @explorer_dar]

@shenfanlaogou 等unsloth的GGUF

[rain cheng @explorer_dar]

@Kimi_Moonshot It release!!!!

[rain cheng @explorer_dar]

@imnotchalk @herdrdev what name is it

[rain cheng @explorer_dar]

@shinonome_tk @akokoi1 I do want

[rain cheng @explorer_dar]

@diegocabezas01 That's too expensive

[rain cheng @explorer_dar]

Why super grok can be subscribed by RMB

[rain cheng @explorer_dar]

The chatgpt new model picker is too hot right?

[rain cheng @explorer_dar]

@mirochill Can be used in the chatgpt app direstly?

[rain cheng @explorer_dar]

when is Deepseek V4 formal version be launched?

[rain cheng @explorer_dar]

还记得你何时加入 X 吗？我知道！#我的X周年纪念日

[rain cheng @explorer_dar]

@videotutor_bsc Will this tool be paid in the future?

[rain cheng @explorer_dar]

It seems like windowOS

[rain cheng @explorer_dar]

what the f**k, I just used $20 in 2 days, and shown me the rate limit